Dongsheng Li

papers

2,086

total citations

papers (29)

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

NEURIPS 2023arXiv

1,267

citations

Rotation-Invariant Transformer for Point Cloud Matching

CVPR 2023arXiv

123

citations

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

CVPR 2021arXiv

113

citations

Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models

AAAI 2024arXiv

citations

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

CVPR 2025arXiv

citations

Disentangled Prompt Representation for Domain Generalization

CVPR 2024

citations

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

AAAI 2024arXiv

citations

VisRL: Intention-Driven Visual Perception via Reinforced Reasoning

ICCV 2025arXiv

citations

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

ICML 2024arXiv

citations

Parameter-free Dynamic Graph Embedding for Link Prediction

NEURIPS 2022arXiv

citations

Recognizing Vector Graphics without Rasterization

NEURIPS 2021arXiv

citations

Reinforcement Learning with Automated Auxiliary Loss Search

NEURIPS 2022arXiv

citations

CNN Kernels Can Be the Best Shapelets

ICLR 2024

citations

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

NEURIPS 2022arXiv

citations

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

ICLR 2025arXiv

citations

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

AAAI 2025arXiv

citations

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

ECCV 2024arXiv

citations

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

CVPR 2025

citations

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

NEURIPS 2023arXiv

citations

RendNet: Unified 2D/3D Recognizer With Latent Space Rendering

CVPR 2022arXiv

citations

Learning to Instruct for Visual Instruction Tuning

NEURIPS 2025arXiv

citations

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference

ICML 2025

citations

Reinforcement Learning Enhanced Explainer for Graph Neural Networks

NEURIPS 2021

citations

Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling

NEURIPS 2023

citations

Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks

NEURIPS 2022

citations

Dongsheng Li

papers (29)

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Rotation-Invariant Transformer for Point Cloud Matching

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration

VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

Bootstrapped Transformer for Offline Reinforcement Learning

Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Disentangled Prompt Representation for Domain Generalization

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

VisRL: Intention-Driven Visual Perception via Reinforced Reasoning

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

Parameter-free Dynamic Graph Embedding for Link Prediction

Recognizing Vector Graphics without Rasterization

Reinforcement Learning with Automated Auxiliary Loss Search

CNN Kernels Can Be the Best Shapelets

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

RendNet: Unified 2D/3D Recognizer With Latent Space Rendering

Learning to Instruct for Visual Instruction Tuning

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference

Reinforcement Learning Enhanced Explainer for Graph Neural Networks

Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling

Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks

papers (29)

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Rotation-Invariant Transformer for Point Cloud Matching

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration

VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

Bootstrapped Transformer for Offline Reinforcement Learning

Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Disentangled Prompt Representation for Domain Generalization

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

VisRL: Intention-Driven Visual Perception via Reinforced Reasoning

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

Parameter-free Dynamic Graph Embedding for Link Prediction

Recognizing Vector Graphics without Rasterization

Reinforcement Learning with Automated Auxiliary Loss Search

CNN Kernels Can Be the Best Shapelets

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

RendNet: Unified 2D/3D Recognizer With Latent Space Rendering

Learning to Instruct for Visual Instruction Tuning

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference

Reinforcement Learning Enhanced Explainer for Graph Neural Networks

Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling

Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks